检索结果-内蒙古大学图书馆

International Conference on parallel Processing (ICPP)

作者： Sayan Ghosh Jeff R. Hammond Antonio J. Peña Pavan Balaji Assefaw H. Gebremedhin Barbara Chapman School of Electrical Engineering and Computer Science Washington State University Pullman WA USA Parallel Computing Lab Intel Corp. Portland OR USA Centro Nacional de Supercomputacion Barcelona ES Mathematics and Computer Science Division Argonne National Laboratory Lemont IL USA Institute for Advanced Computational Science Stony Brook University Stony Brook NY USA

A one-sided programming model separates communication from synchronization, and is the driving principle behind partitioned global address space (PGAS) libraries such as Global Arrays (GA) and SHMEM. PGAS models expose a rich set of functionality that a developer needs in order to implement mathematical algorithms that require frequent multidimensional array accesses. However, use of existing PGAS libraries in application codes often requires significant development effort in order to fully exploit these programming models. On the other hand, a vast majority of scientific codes use MPI either directly or indirectly via third-party scientific computation libraries, and need features to support application-specific communication requirements (e.g., asynchronous update of distributed sparse matrices, commonly arising in machine learning workloads). For such codes it is often impractical to completely shift programming models in favor of special one-sided communication middleware. Instead, an elegant and productive solution is to exploit the one-sided functionality already offered by MPI-3 RMA (Remote Memory Access). We designed a general one-sided interface using the MPI-3 passive RMA model for remote matrix operations in the linear algebra library Elemental, we call the interface we designed RMAInterface. Elemental is an open source library for distributed-memory dense and sparse linear algebra and optimization. We employ RMAInterface to construct a Global Arrays-like API and demonstrate its performance scalability and competitivity with that of the existing GA (with ARMCI-MPI) for a quantum chemistry application.

关键词： Libraries Arrays Two dimensional displays Computational modeling Matrices Data models

来源：评论

学校读者我要写书评

暂无评论

Scalable Bayesian optimization using deep neural networks 32

Scalable Bayesian optimization using deep neural networks

引用

32nd International Conference on Machine Learning, ICML 2015

作者： Snoek, Jasper Ripped, Oren Swersky, Kevin Kiros, Ryan Satish, Nadathur Sundaram, Narayanan Patwary, Md. Mostofa Ali Prabhat Adams, Ryan P. Harvard University School of Engineering and Applied Sciences United States Massachusetts Institute of Technology Department of Mathematics United States University of Toronto Department of Computer Science Canada Intel Labs Parallel Computing Lab Switzerland NERSC Lawrence Berkeley National Laboratory United States

ISBN: (纸本)9781510810587

Bayesian optimization is an effective methodology for the global optimization of functions with expensive evaluations. It relies on querying a distribution over functions defined by a relatively cheap surrogate model. An accurate model for this distribution over functions is critical to the effectiveness of the approach, and is typically fit using Gaussian processes (GPs). However, since GPs scale cubically with the number of observations, it has been challenging to handle objectives whose optimization requires many evaluations, and as such, massively parallelizing the optimization. In this work, we explore the use of neural networks as an alternative to GPs to model distributions over functions. We show that performing adaptive basis function regression with a neural network as the parametric form performs competitively with state-of-the-art GP-based approaches, but scales linearly with the number of data rather than cubically. This allows us to achieve a previously intractable degree of parallelism, which we apply to large scale hyperparameter optimization, rapidly finding competitive models on benchmark object recognition tasks using convolutional networks, and image caption generation using neural language models. © Copyright 2015 by International Machine Learning Society (IMLS). All rights reserved.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Towards a matrix-oriented strided interface in OpenSHMEM 14

Towards a matrix-oriented strided interface in OpenSHMEM

引用

8th International Conference on Partitioned Global Address Space Programming Models, PGAS 2014

作者： Hammond, Jeff R. Extreme Scalability Group Parallel Computing Lab Intel Corporation United States

New communication routines are proposed for OpenSHMEM to allow the efficient implementation of distributed matrix computations. Copyright is held by the owner/author(s). Publication rights licensed to ACM.

ISBN: (纸本)9781450332477

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Sparsifying synchronization for high-performance shared-memory sparse triangular solver

Sparsifying synchronization for high-performance shared-memo...

引用

29th International Supercomputing Conference, ISC 2014

作者： Park, Jongsoo Smelyanskiy, Mikhail Sundaram, Narayanan Dubey, Pradeep Parallel Computing Lab. Intel Corporation Santa Clara CA United States

ISBN: (纸本)9783319075174

The last decade has seen rapid growth of single-chip multiprocessors (CMPs), which have been leveraging Moore's law to deliver high concurrency via increases in the number of cores and vector width. Modern CMPs execute from several hundreds to several thousands concurrent operations per second, while their memory subsystem delivers from tens to hundreds Giga-bytes per second bandwidth. Taking advantage of these parallel resources requires highly tuned parallel implementations of key computational kernels, which form the back-bone of modern HPC. Sparse triangular solver is one such kernel and is the focus of this paper. It is widely used in several types of sparse linear solvers, and it is commonly considered challenging to parallelize and scale even on a moderate number of cores. This challenge is due to the fact that triangular solver typically has limited task-level parallelism and relies on fine-grain synchronization to exploit this parallelism, compared to data-parallel operations such as sparse matrix-vector multiplication. This paper presents synchronization sparsification technique that significantly reduces the overhead of synchronization in sparse triangular solver and improves its scalability. We discover that a majority of task dependencies are redundant in task dependency graphs which are used to model the flow of computation in sparse triangular solver. We propose a fast and approximate sparsification algorithm, which eliminates more than 90% of these dependencies, substantially reducing synchronization overhead. As a result, on a 12-core intel® Xeon® processor, our approach improves the performance of sparse triangular solver by 1.6x, compared to the conventional level-scheduling with barrier synchronization. This, in turn, leads to a 1.4x speedup in a pre-conditioned conjugate gradient solver. © 2014 Springer International Publishing.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Madness: A multiresolution, adaptive numerical environment for scientific simulation

Madness: A multiresolution, adaptive numerical environment f...

引用

作者： Harrison, Robert J. Beylkin, Gregory Bischoff, Florian A. Calvin, Justus A. Fann, George I. Fosso-Tande, Jacob Galindo, Diego Hammond, Jeff R. Hartman-Baker, Rebecca Hill, Judith C. Jia, Jun Kottmann, Jakob S. Ou, M-J. Yvonne Pei, Junchen Ratcliff, Laura E. Reuter, Matthew G. Richie-Halford, Adam C. Romero, Nichols A. Sekino, Hideo Shelton, William A. Sundahl, Bryan E. Thornton, W. Scott Valeev, Edward F. Vázquez-Mayagoitia, Álvaro Vence, Nicholas Yanai, Takeshi Yokoi, Yukina Stony Brook University Stony BrookNY11794 United States University of Colorado at Boulder BoulderCO80309 United States Institut für Chemie Humboldt-Universität Zu Berlin Unter den Linden 6 Berlin10099 Germany Department of Chemistry Virginia Tech. BlacksburgVA24061 United States Oak Ridge National Laboratory Oak RidgeTN37831 United States Department of Chemistry and Biochemistry Florida State University TallahasseeFL32306 United States Parallel Computing Lab Intel Corporation PortlandOR97219 United States National Energy Research Scientific Computing Center Lawrence Berkeley National Laboratory BerkeleyCA94720 United States LinkedIn Mountain ViewCA94043 United States Department of Mathematical Sciences University of Delaware NewarkDE19716 United States State Key Laboratory of Nuclear Physics and Technology School of Physics Peking University Beijing100871 China Argonne Leadership Computing Facility Argonne National Laboratory ArgonneIL60439 United States Department of Physics University of Washington SeattleWA98195 United States Computer Science and Engineering Toyohashi University of Technology ToyohashiAichi441-8580 Japan Louisiana State University Baton RougeLA70803 United States Department of Physics LaSierra University RiversideCA92505 United States Theoretical and Computational Molecular Science Institute for Molecular Science OkazakiAichi444-8585 Japan

MADNESS (multiresolution adaptive numerical environment for scientific simulation) is a high-level software environment for solving integral and differential equations in many dimensions that uses adaptive and fast harmonic analysis methods with guaranteed precision that are based on multiresolution analysis and separated representations. Underpinning the numerical capabilities is a powerful petascale parallel programming environment that aims to increase both programmer productivity and code scalability. This paper describes the features and capabilities of MADNESS and briefly discusses some current applications in chemistry and several areas of physics. © 2016 Society for Industrial and Applied Mathematics.

关键词： Multiresolution analysis

来源：评论

学校读者我要写书评

暂无评论

To INT-MAX... and Beyond! Exploring Large-Count Support in MPI

To INT-MAX... and Beyond! Exploring Large-Count Support in M...

引用

2014 Workshop on Exascale MPI at Supercomputing Conference, ExaMPI 2014

作者： Hammond, Jeff R. Schafer, Andreas Latham, Rob Parallel Computing Lab Intel Corp. Switzerland Friedrich-Alexander-Universitat Erlangen-Nurnberg Germany Mathmatics and Computer Science Division Argonne National Lab. United States

ISBN: (纸本)9781479970322

In order to describe a structured region of memory, the routines in the MPI standard use a (count, datatype) pair. The C specification for this convention uses an int type for the count. Since C int types are nearly always 32 bits large and signed, counting more than 231 elements poses a challenge. Instead of changing the existing MPI routines, and all consumers of those routines, the MPI Forum asserts that users can build up large datatypes from smaller types. To evaluate this hypothesis and to provide a user-friendly solution to the large-count issue, we have developed BigMPI, a library on top of MPI that maps large-count MPI-like functions to MPI-3 standard features. BigMPI demonstrates a way to perform such a construction, reveals shortcomings of the MPI standard, and uncovers bugs in MPI implementations. © 2014 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Clique guided community detection

Clique guided community detection

引用

IEEE International Conference on Big Data

作者： Diana Palsetia Md. Mostofa Ali Patwary William Hendrix Ankit Agrawal Alok Choudhary Northwestern University Evanston IL Parallel Computing Lab Intel Santa Clara CA

Discovering communities to understand and model network structures has been a fundamental problem in several fields including social networks, physics, and biology. Many algorithms have been developed for finding the communities. Modularity based technique is fairly new relative to clustering, though it is very popular currently. Although some fast modularity based algorithms exist for detecting communities, the quality of these solutions is limited. At the other extreme, a clique embodies a basic community as it has the greatest possible edge density. However, the requirement that each pair of vertices be connected is too strict. Therefore, techniques to merge partitioned cliques using a hill-climbing greedy algorithm have been studied to form communities. However, the task of finding cliques is computationally expensive. In this paper, we present a new approach for fast and efficient community detection. We propose a clique guided community detection framework that consists of two phases. In the first phase, the framework finds disjoint cliques. In the second phase, the cliques from the first phase are used to guide the merging of individual vertices until a good quality solution is obtained. For the first phase, we develop an algorithm named MaCH (Maximum Clique Heuristic), which is a new approach to compute disjoint cliques using a heuristic-based branch-and-bound technique. We provide experimental results to demonstrate the efficiency of the new algorithm and compare our approach with other previously proposed algorithms.

关键词： Communities Heuristic algorithms Merging Partitioning algorithms Clustering algorithms Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

To INT_MAX... and Beyond! Exploring Large-Count Support in MPI

To INT_MAX... and Beyond! Exploring Large-Count Support in M...

引用

Workshop on Exascale MPI at Supercomputing Conference (ExaMPI)

作者： Jeff R. Hammond Andreas Schäfer Rob Latham Parallel Computing Lab Intel Corp Friedrich-Alexander-Universität Erlangen-Nürnberg

关键词： Vectors Standards Libraries Optimization Context Memory management Open area test sites

来源：评论

学校读者我要写书评

暂无评论

Beacon: Exploring the Deployment and Application of intel Xeon Phi Coprocessors for Scientific computing

引用

computing in Science & Engineering 2015年第2期17卷 1-1页

作者： R. Glenn Brook Alexander Heinecke Anthony B. Costa Paul Peltz Vincent C. Betro Troy Baer Michael Bader Pradeep Dubey University of Tennessee Knoxville Intel's Parallel Computing Lab Mount Sinai's Icahn School of Medicine at Mount Sinai Technische Universität München

The Beacon Project is exploring the impact of the intel Xeon Phi coprocessor on scientific supercomputing for a wide variety of computational science and engineering applications.

关键词： Random access memory Coprocessors Scientific computing High performance computing Electrostatics Computer architecture Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Delayed Difference Scheme for Large Scale Scientific Simulations

引用

Physical Review Letters 2014年第21期113卷 218701-218701页

作者： Dheevatsa Mudigere Sunil D. Sherlekar Santosh Ansumali Parallel Computing Lab Intel Labs Bangalore 560103 India Engineering Mechanics Unit Jawaharlal Nehru Centre for Advanced Scientific Research Jakkur Bangalore 560064 India

We argue that the current heterogeneous computing environment mimics a complex nonlinear system which needs to borrow the concept of time-scale separation and the delayed difference approach from statistical mechanics and nonlinear dynamics. We show that by replacing the usual difference equations approach by a delayed difference equations approach, the sequential fraction of many scientific computing algorithms can be substantially reduced. We also provide a comprehensive theoretical analysis to establish that the error and stability of our scheme is of the same order as existing schemes for a large, well-characterized class of problems.

关键词： HETEROGENEOUS computing COMPUTER algorithms NONLINEAR dynamical systems STATISTICAL mechanics DIFFERENCE equations

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：